[1]郭玉娣,李根,李春,等.基于多时相合成孔径雷达数据的水稻种植面积监测[J].江苏农业学报,2023,(05):1179-1188.[doi:doi:10.3969/j.issn.1000-4440.2023.05.010]
　GUO Yu-di,LI Gen,LI Chun,et al.Rice planting area monitoring based on multi-temporal synthetic aperture radar (SAR) data[J].,2023,(05):1179-1188.[doi:doi:10.3969/j.issn.1000-4440.2023.05.010]
点击复制

基于多时相合成孔径雷达数据的水稻种植面积监测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年05期
页码:
1179-1188
栏目:
农业信息工程
出版日期:
2023-08-31

文章信息/Info

Title:
Rice planting area monitoring based on multi-temporal synthetic aperture radar (SAR) data
作者:
郭玉娣1; 2; 李根1; 2; 李春1; 梁冬坡1; 2
（1.天津市气候中心，天津300074；2.高分辨率对地观测系统天津数据与应用中心，天津300074）
Author(s):
GUO Yu-di1; 2; LI Gen1; 2; LI Chun1; LIANG Dong-po1; 2
(1.Tianjin Climate Center, Tianjin 300074, China;2.High Resolution Earth Observation System Tianjin Data and Application Center, Tianjin 300074, China)
关键词:
合成孔径雷达; 随机森林; 相似性指数; 水稻种植面积提取
Keywords:
synthetic aperture radar; random forest; similarity index; rice planting area extraction
分类号:
S127
DOI:
doi:10.3969/j.issn.1000-4440.2023.05.010
文献标志码:
A
摘要:
与光学遥感相比，合成孔径雷达（SAR）遥感能够不受云雨天气影响，为大范围作物种植信息的精准监测提供新手段。本研究以天津市小站稻为例，基于2018-2021年的多时相Sentinel-1A SAR影像，提出了结合小站稻生长特征相似性分析与随机森林分类的水稻种植分布和面积监测方法。首先提取VV和VH极化方式下不同地物的后向散射系数时间序列特征曲线，并利用HANTS滤波来消除噪声影响。然后根据野外调查数据获取小站稻参考生长曲线，构建小站稻相似性指数，筛选出小站稻可能种植区域。最后采用随机森林分类模型提取小站稻种植面积。结果表明，基于多时相Sentinel-1A SAR影像相似性分析及随机森林分类能够获得较高精度的水稻种植面积，VV和VH两种极化方式下提取的水稻种植面积与统计年鉴结果的平均相对误差分别为2.67%和3.80%，总体分类精度分别达到95.52%和93.40%，Kappa系数分别为0.94和0.93；与不引入相似性指数进行分类相比，VV和VH极化方式下引入相似性指数后总体分类精度分别提高4.35个百分点和3.13个百分点，Kappa系数分别提高0.04和0.03，水稻的制图精度分别提高3.38个百分点和3.25个百分点。本研究结果为开展高精度水稻种植信息业务化监测提供参考。
Abstract:
Compared with optical remote sensing, synthetic aperture radar (SAR) remote sensing can not be affected by cloud and rain, which provides a new means for accurate monitoring of large-scale crop planting information. Based on the multi-temporal Sentinel-1A SAR image data from 2018 to 2021, a new method for monitoring the planting distribution and area was proposed with Xiaozhan rice in Tianjin as an example, which combined the similarity analysis of growth characteristics with random forest classification. Firstly, the backscattering coefficient time series characteristic curves of different ground objects under VV and VH polarization modes were extracted, and HANTS filtering was used to eliminate the effect of noise. Then, according to the field survey data, the reference growth curve of Xiaozhan rice was obtained and the similarity index of Xiaozhan rice was constructed to screen out the possible planting areas of Xiaozhan rice. Finally, random forest classification model was used to extract the planting area of Xiaozhan rice. The results showed that the multi-temporal Sentinel-1A SAR image similarity analysis combined with random forest classification could obtain high precision rice planting information. The average relative errors of rice planting area extracted by VV and VH polarization methods with the statistical data were 2.67% and 3.80%, respectively. The overall classification accuracies were 95.52% and 93.40%, respectively, and the Kappa coefficients were 0.94 and 0.93, respectively. Compared with the classification results without similarity index, the overall classification accuracy with similarity index under VV and VH polarization modes increased by 4.35 percentage points and 3.13 percentage points, the Kappa coefficients increased by 0.04 and 0.03, and the mapping accuracy of rice increased by 3.38 percentage points and 3.25 percentage points，respectively. The results of this study provide a reference for future business monitoring of high-precision rice planting information.

参考文献/References:

[1]郭云峰，王凤行，陈子学，等.天津小站稻发展现状与振兴策略[J].作物研究,2021,35(5):431-435.
[2]王人潮，黄敬峰. 水稻遥感估产[M]. 北京：中国农业出版社，2002.
[3]XIAO X，BOLES S，LIU J，et al.Mapping paddy rice agriculture in southern China using multi-temporal MODIS images[J].Remote Sensing of Environment，2005，95(4)：480-492.
[4]刘佳，王利民，姚保民，等. 基于多时相OLI数据的宁夏大尺度水稻面积遥感估算[J]. 农业工程学报，2017，33（15）：200-209.
[5]杨沈斌，景元书，王琳，等.基于MODIS时序时间提取河南省水稻种植分布[J].大气科学学报，2012，35(1)：113-120.
[6]李根，景元书，王琳，等. 基于MODIS时序植被指数和线性光谱混合模型的水稻面积提取[J]. 大气科学学报, 2014, 37(1):119-126.
[7]张晓忆，李卫国，景元书，等.多种光谱指标构建决策树的水稻种植面积提取[J].江苏农业学报，2016，32(5):1066-1072.
[8]CAO J J，CAI X L，TAN J W，et al.Mapping paddy rice using Landsat time series data in the Ganfu Plain irrigation system，Southern China，from 1988-2017[J].International Journal of Remote Sensing，2021,42(4):1556-1576.
[9]曹丹，白林燕，冯建中，等.东北三省水稻种植面积时空变化监测与分析[J].江苏农业科学，2018,46(10):260-265.
[10]王松寒，何隆华.雷达遥感技术在水稻识别中的研究进展[J].遥感信息，2015,30(2):3-9.
[11]张征云，江文渊，张彦敏，等.基于哨兵SAR数据和多光谱数据的水稻识别研究[J].生态与农村环境学报,2023,39(4):556-564.
[12]SHAO Y, FAN X, LIU H, et al. Rice monitoring and production estimation using multitemporal RADARSAT[J].Remote Sensing of Environment, 2001, 76(3): 310-325.
[13]申双和，杨沈斌，李秉柏，等. 基于ENVISAT ASAR数据的水稻估产方案[J]. 中国科学（D辑：地球科学），2009,39(6):763-773.
[14]杨沈斌，李秉柏，申双和，等. 基于多时相多极化差值图的稻田识别研究[J]. 遥感学报，2008,13(3):138-144.
[15]CLAUSS K, OTTINGER M, LEINENKUGEL P, et al. Estimating rice production in the Mekong Delta, Vietnam, utilizing time series of Sentinel-1 SAR data[J]. International Journal of Applied Earth Observation and Geoinformation, 2018,73:574-585.
[16]黄翀，许照鑫，张晨晨,等. 基于Sentinel-1数据时序特征的热带地区水稻种植结构提取方法[J]. 农业工程学报, 2020, 36(9):177-184.
[17]桑国庆，唐志光，毛克彪,等. 基于GEE云平台与Sentinel数据的高分辨率水稻种植范围提取——以湖南省为例[J]. 作物学报, 2022, 48(9):2409-2420.
[18]夏俊，苏涛，刘丽娜，等. 基于多时相Sentinel-1A数据的水稻面积提取[J].江苏农业学报, 2022,38(3):666-674.
[19]查东平，蔡海生，张学玲,等. 基于多时相Sentinel-1水稻种植范围提取[J].自然资源遥感, 2022,34(3):184-195.
[20]杜伟娜，徐爱功，宋耀鑫,等.新型SAR传感器一级地距产品绝对辐射定标方法[J].国土资源遥感,2016,28(4):30-34.
[21]刘海娟，张婷，侍昊，等. 基于RF模型的高分辨率遥感影像分类评价[J].南京林业大学学报(自然科学版)，2015,39(1):99-103.
[22]WATTS J D, POWELL S L, LAWRENCE R L, et al. Improved classification of conservation tillage adoption using high temporal and synthetic satellite imagery[J]. Remote Sensing of Environment, 2011, 115(1):66-75.
[23]BREIMAN L, LAST M, RICE J. Random forests: Finding quasars//[M]. FEIGELSON E D, BABU G J. Statistical Challenges in Astronomy. New York: Springer, 2003:243-254.
[24]周正龙，沙晋明，范跃新，等. 基于随机森林的遥感土地利用分类及景观格局分析[J].计算机系统应用,2020,29(2):40-48.

相似文献/References:

[1]牛芳鹏,李新国,麦麦提吐尔逊·艾则孜,等.基于光谱指数的博斯腾湖西岸湖滨绿洲土壤有机碳含量估算模型[J].江苏农业学报,2022,38(02):414.[doi:doi:10.3969/j.issn.1000-4440.2022.02.015]
　NIU Fang-peng,LI Xin-guo,MAMATTURSUN·Eziz,et al.Estimation model of soil organic carbon content in lakeside oasis on the west coast of Bosten Lake based on spectral index[J].,2022,38(05):414.[doi:doi:10.3969/j.issn.1000-4440.2022.02.015]
[2]李长春,翟伟广,王春阳,等.基于Sentinel-1A影像的原阳县玉米和水稻分类时间窗选择[J].江苏农业学报,2023,(02):413.[doi:doi:10.3969/j.issn.1000-4440.2023.02.014]
　LI Chang-chun,ZHAI Wei-guang,WANG Chun-yang,et al.Time window selection of corn and rice classification in Yuanyang County based on Sentinel-1A image[J].,2023,(05):413.[doi:doi:10.3969/j.issn.1000-4440.2023.02.014]
[3]樊泳灼,李新国.湖滨绿洲棕漠土有机碳含量高光谱估算[J].江苏农业学报,2023,(06):1341.[doi:doi:10.3969/j.issn.1000-4440.2023.06.009]
　FAN Yong-zhuo,LI Xin-guo.Hyperspectral prediction of organic carbon content of brown desert soil in the lakeside oasis[J].,2023,(05):1341.[doi:doi:10.3969/j.issn.1000-4440.2023.06.009]
[4]钟怡琪,李家国,韩杰,等.基于哨兵影像与多特征优选的溧阳市上兴镇水稻识别[J].江苏农业学报,2023,(08):1688.[doi:doi:10.3969/j.issn.1000-4440.2023.08.008]
　ZHONG Yi-qi,LI Jia-guo,HAN Jie,et al.Identification of rice in Shangxing Town, Liyang City based on Sentinel image and multi-feature optimization[J].,2023,(05):1688.[doi:doi:10.3969/j.issn.1000-4440.2023.08.008]

备注/Memo

备注/Memo:
收稿日期：2022-02-28 基金项目：国家自然科学基金项目（31901398）；天津市气象局一般项目（202222ybxm13）作者简介：郭玉娣（1988- ），江苏盐城人，硕士，工程师，主要从事遥感应用研究。（E-mail）guoyudi.0802@163.com 通讯作者：李根，（E-mail）ligen_zt@163.com
更新日期/Last Update: 2023-09-13